{"id":"W2468840277","doi":"10.18653/v1/s16-1151","title":"CLaC at SemEval-2016 Task 11: Exploring linguistic and psycho-linguistic Features for Complex Word Identification","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"SemEval; Task (project management); Computer science; Natural language processing; Identification (biology); Word (group theory); Context (archaeology); Artificial intelligence; Ranking (information retrieval); Random forest; Linguistics; History","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003299456,0.00341166,0.001836872,0.002595014,0.001379572,0.003246902,0.002550147,0.003373108,0.02081035],"category_scores_gemma":[0.01218396,0.0007064026,0.001699197,0.001262046,0.0006390254,0.004533738,0.003772853,0.003069598,0.02090353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00120268,"about_ca_system_score_gemma":0.001853785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008314414,"about_ca_topic_score_gemma":0.01483239,"domain_scores_codex":[0.997269,0.0007689238,0.0001975427,0.001046608,0.0004789899,0.0002389223],"domain_scores_gemma":[0.9949118,0.00232533,0.0002373816,0.001127704,0.0009410965,0.0004567139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003123536,0.001526554,0.01669638,0.002718774,0.0004801673,0.0009659003,0.001150154,0.007374994,0.04331883,0.002844527,0.3394215,0.5803788],"study_design_scores_gemma":[0.001769667,0.002496602,0.09188937,0.0008797539,0.0006463769,0.006193645,0.003321089,0.4650378,0.1095267,0.02686013,0.290464,0.0009147762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4307647,0.007743961,0.1696803,0.002711648,0.003416563,0.003718055,0.1314178,0.1889637,0.06158335],"genre_scores_gemma":[0.511628,0.000735951,0.2176451,0.001433664,0.0004225812,0.002216992,0.2402337,0.005155355,0.02052848],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02081035,"threshold_uncertainty_score":0.06961751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06689074162379126,"score_gpt":0.3392053747066378,"score_spread":0.2723146330828465,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}